Jindong Wang

Anyone interested in transfer learning is welcomed to contribute to this repo (by pull request): - You can add the latest publications / tools / tutorials directly to `readme.md` and...

Some questions about GAN code

1

In the [GAN code](https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/03-advanced/generative_adversarial_network/main.py#L41-L57), why L98 is repeated in L115? I tried to delete L115, it works fine. Is there something I miss?

欢迎提意见！

39

由于作者水平有限，错误、不足之处请多提意见！ 如果有任何建议（新方法、新数据、新竞赛等任何新的东西），也欢迎到这里留言！

参与贡献方式 How to contribute

26

请在此issue下留言你的github账号和邮箱，我将你加入到协作者中。

Loss is becoming negative

3

Very nice work! During my training, I found that loss can become negative: ``` Train Epoch: 198 [0/100 (0%)] Loss1: 0.024868 Loss2: 0.022132 Discrepancy: 0.018226 Test set: Average loss: -0.0588,...

在知乎上看到这个工作，非常开心，Matlab终于也有做深度学习的工具了，虽然刚刚起步，预测前景一定不错。在这里斗胆提几点小建议： 1.Logo太丑了，真心和这个时代不符，参考一下tensorflow和mxnet这些，简洁一点好看一点吧。。。 2.代码组织上，一个.m一个function，那得多少啊。。。适当封装一些sub-function吧； 3.有没有可能一起开发？